sheets-artifact
Pass
Audited by Gen Agent Trust Hub on Oct 5, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to read, inspect, and extract data from external spreadsheet files (Excel, Google Sheets, CSV). This creates a vulnerability surface where a malicious spreadsheet could contain embedded instructions intended to influence or override the agent's behavior during processing.
- Ingestion points: Reading, extracting, and reviewing workbook data as described in
SKILL.md. - Boundary markers: The skill does not define specific delimiters or "ignore embedded instructions" warnings for the content read from workbooks.
- Capability inventory: The skill has the capability to edit files, change access permissions for shared documents, and handle sensitive data (e.g., salary information).
- Sanitization: No explicit sanitization or filtering of spreadsheet content is defined in this instruction file.
Audit Metadata